Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2053 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1241861 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1254176 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1215. Min Act: -0.0001

Data Index: 942903 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1246538 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1022. Min Act: -0.0002

Data Index: 483522 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0962. Min Act: -0.0001

Data Index: 908230 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1067. Min Act: -0.0001

Data Index: 668431 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1141826 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1048. Min Act: -0.0002

Data Index: 844544 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1039. Min Act: -0.0002

Data Index: 429411 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0989. Min Act: -0.0002

Data Index: 86669 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0957. Min Act: -0.0001

Data Index: 494111 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1050900 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0945. Min Act: -0.0001

Data Index: 985070 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0980. Min Act: -0.0002

Data Index: 585795 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1052. Min Act: -0.0002

Data Index: 824458 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0947. Min Act: -0.0002

Data Index: 678147 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0926. Min Act: -0.0001

Data Index: 561148 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1200345 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1079021 (C4 (Web Text))

Max Activating Token Index: 947